Downloads · 30 days
16
2% of all-time downloads
LocateAnything-Qwen2-FP8
shigureui/LocateAnything-Qwen2-FP8
LocateAnything-Qwen2-FP8 is a machine learning model from shigureui. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
All-time downloads
1K
Public
Parameters
3.4B
4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors4 GB · 100%
Parameter types
How the weights are stored.
F8_E4M32.8B · 82%
Base models
Model card
From the Hugging Face model README
FP8 version made for LocateAnything
made by https://github.com/WuNein/LocateAnything-vLLM
vllm serve locate_qwen2_model --tensor-parallel-size 1 --max-model-len 8192 --gpu-memory-utilization 0.5 --kv-cache-dtype auto --max-model-len 16384 --max-num-seqs 32 --max-cudagraph-capture-size 32 --enable-prompt-embeds
- Type
- qwen2
- License
- apache-2.0
- Created
- Jun 6, 2026
- Updated
- Jun 6, 2026